Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.7394. Min Act: -0.1700
Data Index: 7112128 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.3956. Min Act: -0.1700
Data Index: 5468271 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.3956. Min Act: -0.1700
Data Index: 3881340 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.3331. Min Act: -0.1700
Data Index: 4338664 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.3019. Min Act: -0.1700
Data Index: 5760873 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.3019. Min Act: -0.1700
Data Index: 328759 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.3019. Min Act: -0.1700
Data Index: 3948998 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.2706. Min Act: -0.1700
Data Index: 8298977 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.2394. Min Act: -0.1700
Data Index: 8006585 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.2394. Min Act: -0.1700
Data Index: 1331022 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.2081. Min Act: -0.1700
Data Index: 395971 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.2081. Min Act: -0.1700
Data Index: 3985162 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.2081. Min Act: -0.1700
Data Index: 3127784 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.2081. Min Act: -0.1700
Data Index: 2244941 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.2081. Min Act: -0.1700
Data Index: 7294303 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.2081. Min Act: -0.1700
Data Index: 6694585 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.2081. Min Act: -0.1700
Data Index: 3686589 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.2081. Min Act: -0.1700
Data Index: 7444511 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.1769. Min Act: -0.1700
Data Index: 259615 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7394. Min Range: -5.7394
Max Act: 5.1769. Min Act: -0.1700
Data Index: 2013595 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19